Event generator tuning using Bayesian optimization

Abstract

Monte Carlo event generators contain a large number of parameters that must be determined by comparing the output of the generator with experimental data. Generating enough events with a fixed set of parameter values to enable making such a comparison is extremely CPU intensive, which prohibits performing a simple brute-force grid-based tuning of the parameters. Bayesian optimization is a powerful method designed for such black-box tuning applications. In this article, we show that Monte Carlo event generator parameters can be accurately obtained using Bayesian optimization and minimal expert-level physics knowledge. A tune of the PYTHIA 8 event generator using $e^{+}{e}^{-}$ events, where 20 parameters are optimized, can be run on a modern laptop in just two days. Combining the Bayesian optimization approach with expert knowledge should enable producing better tunes in the future, by making it faster and easier to study discrepancies between Monte Carlo and experimental data.

25 pages, 14 figures, 5 tables; v2 updated to journal version

References in corpus (4)

• Practical Bayesian Optimization of Machine Learning Algorithms
• An Introduction to PYTHIA 8.2
• Tuning PYTHIA 8.1: the Monash 2013 Tune
• Event generator tunes obtained from underlying event and multiparton scattering measurements

Cited by in corpus (19)

• Machine learning and the physical sciences
• Deep Learning and its Application to LHC Physics
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• Event Generators for High-Energy Physics Experiments
• Towards a Deep Learning Model for Hadronization
• Machine Learning in High Energy Physics Community White Paper
• AI-optimized detector design for the future Electron-Ion Collider: the dual-radiator RICH case
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• Bayesian optimization in ab initio nuclear physics
• High dimensional parameter tuning for event generators
• Towards a data-driven model of hadronization using normalizing flows
• Measurement of groomed event shape observables in deep-inelastic electron-proton scattering at HERA
• A Bayesian tune of the Herwig Monte Carlo event generator
• Strategic Plan for a Scientific Software Innovation Institute (S2I2) for High Energy Physics
• Describing Hadronization via Histories and Observables for Monte-Carlo Event Reweighting
• Efficient Transfer Bayesian Optimization with Auxiliary Information
• Adaptive Divergence for Rapid Adversarial Optimization
• Monte Carlo Event Generators for Future Lepton Colliders
• Improved tuning methods for Monte Carlo generators